Triple
T7914800
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martha McMillan Roberts |
E183792
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | FSA |
E486034
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: FSA | Statement: [Martha McMillan Roberts, employer, FSA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: FSA Context triple: [Martha McMillan Roberts, employer, FSA]
-
A.
FSA
FSA is the independent UK government body responsible for protecting public health and consumer interests in relation to food.
-
B.
FSA
FSA is the abbreviation for the former U.S. Federal Security Agency, a government body that once oversaw various federal social and public health programs.
-
C.
FSA
FSA is the commonly used acronym for the First Step Act, a major U.S. federal criminal justice reform law enacted in 2018.
-
D.
FSA
chosen
FSA is a postnominal designation indicating fellowship in the Society of Antiquaries of London, a learned society dedicated to the study of the material remains of the past.
-
E.
FSA
FSA is the U.S. Department of Education office that manages federal financial aid programs for students pursuing postsecondary education.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca828efbe48190bd48482650182e79 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3a759b548190af2e2aa0705d7051 |
completed | March 31, 2026, 3:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb5be54fdc81909a988114a6f30a13 |
completed | March 31, 2026, 5:30 a.m. |
Created at: March 30, 2026, 5:05 p.m.